Repository files navigation
ExpectiMinimaxOptimal strategy in games with chance nodes , MelkΓ³ E., Nagy B. (2007).Sparse samplingA sparse sampling algorithm for near-optimal planning in large Markov decision processes , Kearns M. et al. (2002).MCTSEfficient Selectivity and Backup Operators in Monte-Carlo Tree Search , RΓ©mi Coulom, SequeL (2006).UCTBandit based Monte-Carlo Planning , Kocsis L., SzepesvΓ‘ri C. (2006).Bandit Algorithms for Tree Search , Coquelin P-A., Munos R. (2007).OPDOptimistic Planning for Deterministic Systems , Hren J., Munos R. (2008).OLOPOpen Loop Optimistic Planning , Bubeck S., Munos R. (2010).SOOPOptimistic Planning for Continuous-Action Deterministic Systems , BuΕoniu L. et al. (2011).OPSSOptimistic planning for sparsely stochastic systems , L. BuΕoniu, R. Munos, B. De Schutter, and R. Babuska (2011).HOOTSample-Based Planning for Continuous ActionMarkov Decision Processes , Mansley C., Weinstein A., Littman M. (2011).HOLOPBandit-Based Planning and Learning inContinuous-Action Markov Decision Processes , Weinstein A., Littman M. (2012).BRUESimple Regret Optimization in Online Planning for Markov Decision Processes , Feldman Z. and Domshlak C. (2014).LGPLogic-Geometric Programming: An Optimization-Based Approach to Combined Task and Motion Planning , Toussaint M. (2015). ποΈ AlphaGoMastering the game of Go with deep neural networks and tree search , Silver D. et al. (2016).AlphaGo ZeroMastering the game of Go without human knowledge , Silver D. et al. (2017).AlphaZeroMastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm , Silver D. et al. (2017).TrailBlazerBlazing the trails before beating the path: Sample-efficient Monte-Carlo planning , Grill J. B., Valko M., Munos R. (2017).MCTSnetsLearning to search with MCTSnets , Guez A. et al. (2018).ADISolving the Rubik's Cube Without Human Knowledge , McAleer S. et al. (2018).OPC/SOPCContinuous-action planning for discounted inο¬nite-horizon nonlinear optimal control with Lipschitz values , BuΕoniu L., Pall E., Munos R. (2018).Real-time tree search with pessimistic scenarios: Winning the NeurIPS 2018 Pommerman Competition , Osogami T., Takahashi T. (2019)
(book) The Mathematical Theory of Optimal Processes , L. S. Pontryagin, Boltyanskii V. G., Gamkrelidze R. V., and Mishchenko E. F. (1962).
(book) Constrained Control and Estimation , Goodwin G. (2005).
PIΒ²A Generalized Path Integral Control Approach to Reinforcement Learning , Theodorou E. et al. (2010).PIΒ²-CMAPath Integral Policy Improvement with Covariance Matrix Adaptation , Stulp F., Sigaud O. (2010).iLQGA generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems , Todorov E. (2005). iLQG+Synthesis and stabilization of complex behaviors through online trajectory optimization , Tassa Y. (2012).
Minimax analysis of stochastic problems , Shapiro A., Kleywegt A. (2002).Robust DPRobust Dynamic Programming , Iyengar G. (2005).Robust Planning and Optimization , Laumanns M. (2011). (lecture notes)Robust Markov Decision Processes , Wiesemann W., Kuhn D., Rustem B. (2012).Safe and Robust Learning Control with Gaussian Processes , Berkenkamp F., Schoellig A. (2015). ποΈ Tube-MPPIRobust Sampling Based Model Predictive Control with Sparse Objective Information , Williams G. et al. (2018). ποΈ Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning , Lukas Bronke et al. (2021).
A Comprehensive Survey on Safe Reinforcement Learning , GarcΓa J., FernΓ‘ndez F. (2015).RA-QMDPRisk-averse Behavior Planning for Autonomous Driving under Uncertainty , Naghshvar M. et al. (2018).StoROOX-Armed Bandits: Optimizing Quantiles and Other Risks , Torossian L., Garivier A., Picheny V. (2019).Worst Cases Policy Gradients , Tang Y. C. et al. (2019).Model-Free Risk-Sensitive Reinforcement Learning , DelΓ©tang G. et al. (2021).Optimal Thompson Sampling strategies for support-aware CVaR bandits , Baudry D., Gautron R., Kaufmann E., Maillard O. (2021).
Value-Constrained Control
ICSWill the Driver Seat Ever Be Empty? , Fraichard T. (2014).SafeOPTSafe Controller Optimization for Quadrotors with Gaussian Processes , Berkenkamp F., Schoellig A., Krause A. (2015). ποΈ SafeMDPSafe Exploration in Finite Markov Decision Processes with Gaussian Processes , Turchetta M., Berkenkamp F., Krause A. (2016). RSSOn a Formal Model of Safe and Scalable Self-driving Cars , Shalev-Shwartz S. et al. (2017).CPOConstrained Policy Optimization , Achiam J., Held D., Tamar A., Abbeel P. (2017). RCPOReward Constrained Policy Optimization , Tessler C., Mankowitz D., Mannor S. (2018).BFTQA Fitted-Q Algorithm for Budgeted MDPs , Carrara N. et al. (2018).SafeMPCLearning-based Model Predictive Control for Safe Exploration , Koller T, Berkenkamp F., Turchetta M. Krause A. (2018).CCEConstrained Cross-Entropy Method for Safe Reinforcement Learning , Wen M., Topcu U. (2018). LTL-RLReinforcement Learning with Probabilistic Guarantees for Autonomous Driving , Bouton M. et al. (2019).Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments , Bouton M. et al. (2019). Batch Policy Learning under Constraints , Le H., Voloshin C., Yue Y. (2019).Value constrained model-free continuous control , Bohez S. et al (2019). ποΈ Safely Learning to Control the Constrained Linear Quadratic Regulator , Dean S. et al (2019).Learning to Walk in the Real World with Minimal Human Effort , Ha S. et al. (2020) ποΈ Responsive Safety in Reinforcement Learning by PID Lagrangian Methods , Stooke A., Achiam J., Abbeel P. (2020). Envelope MOQ-LearningA Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation , Yang R. et al (2019).
State-Constrained Control and Stability Uncertain Dynamical Systems
TSOn the Likelihood that One Unknown Probability Exceeds Another in View of the Evidence of Two Samples , Thompson W. (1933).Exploration and Exploitation in Organizational Learning , March J. (1991).UCB1 / UCB2Finite-time Analysis of the Multiarmed Bandit Problem , Auer P., Cesa-Bianchi N., Fischer P. (2002).Empirical Bernstein / UCB-VExploration-exploitation tradeoff using variance estimates in multi-armed bandits , Audibert J-Y, Munos R., Szepesvari C. (2009).Empirical Bernstein Bounds and Sample Variance Penalization , Maurer A., Ponti M. (2009).An Empirical Evaluation of Thompson Sampling , Chapelle O., Li L. (2011).kl-UCBThe KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond , Garivier A., CappΓ© O. (2011).KL-UCBKullback-Leibler Upper Confidence Bounds for Optimal Sequential Allocation , CappΓ© O. et al. (2013).IDSInformation Directed Sampling and Bandits with Heteroscedastic Noise Kirschner J., Krause A. (2018).
Best Arm Identification πͺ
Successive EliminationAction Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems , Even-Dar E. et al. (2006).LUCBPAC Subset Selection in Stochastic Multi-armed Bandits , Kalyanakrishnan S. et al. (2012).UGapEBest Arm Identification: A Unified Approach to Fixed Budget and Fixed Confidence , Gabillon V., Ghavamzadeh M., Lazaric A. (2012).Sequential HalvingAlmost Optimal Exploration in Multi-Armed Bandits , Karnin Z. et al (2013).M-LUCB / M-RacingMaximin Action Identification: A New Bandit Framework for Games , Garivier A., Kaufmann E., Koolen W. (2016).Track-and-StopOptimal Best Arm Identification with Fixed Confidence , Garivier A., Kaufmann E. (2016).LUCB-microStructured Best Arm Identification with Fixed Confidence , Huang R. et al. (2017).
Black-box Optimization β¬
GP-UCBGaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design , Srinivas N., Krause A., Kakade S., Seeger M. (2009).HOOXβArmed Bandits , Bubeck S., Munos R., Stoltz G., Szepesvari C. (2009).DOO/SOOOptimistic Optimization of a Deterministic Function without the Knowledge of its Smoothness , Munos R. (2011).StoOOFrom Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning , Munos R. (2014).StoSOOStochastic Simultaneous Optimistic Optimization , Valko M., Carpentier A., Munos R. (2013).POOBlack-box optimization of noisy functions with unknown smoothness , Grill J-B., Valko M., Munos R. (2015).EI-GPBayesian Optimization in AlphaGo , Chen Y. et al. (2018)
Reinforcement Learning π€
Expected mistake bound model for on-line reinforcement learning , Fiechter C-N. (1997).UCRL2Near-optimal Regret Bounds for Reinforcement Learning , Jaksch T. (2010). PSRLWhy is Posterior Sampling Better than Optimism for Reinforcement Learning? , Osband I., Van Roy B. (2016). UCBVIMinimax Regret Bounds for Reinforcement Learning , Azar M., Osband I., Munos R. (2017). Q-Learning-UCBIs Q-Learning Provably Efficient? , Jin C., Allen-Zhu Z., Bubeck S., Jordan M. (2018). LSVI-UCBProvably Efficient Reinforcement Learning with Linear Function Approximation , Jin C., Yang Z., Wang Z., Jordan M. (2019). Lipschitz Continuity in Model-based Reinforcement Learning , Asadi K. et al (2018).On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces , Yang Z., Jin C., Wang Z., Wang M., Jordan M. (2021)
PAC Adaptive Control of Linear Systems , Fiechter C.-N. (1997)OFU-LQRegret Bounds for the Adaptive Control of Linear Quadratic Systems , Abbasi-Yadkori Y., Szepesvari C. (2011).TS-LQImproved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems , Abeille M., Lazaric A. (2018).Exploration-Exploitation with Thompson Sampling in Linear Systems , Abeille M. (2017). (phd thesis)Coarse-IdOn the Sample Complexity of the Linear Quadratic Regulator , Dean S., Mania H., Matni N., Recht B., Tu S. (2017).Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator , Dean S. et al (2018).Robust exploration in linear quadratic reinforcement learning , Umenberger J. et al (2019).Online Control with Adversarial Disturbances , Agarwal N. et al (2019). Logarithmic Regret for Online Control , Agarwal N. et al (2019).
ACPolicy Gradient Methods for Reinforcement Learning with Function Approximation , Sutton R. et al. (1999).NACNatural Actor-Critic , Peters J. et al. (2005).DPGDeterministic Policy Gradient Algorithms , Silver D. et al. (2014).DDPGContinuous Control With Deep Reinforcement Learning , Lillicrap T. et al. (2015). ποΈ 1 |Β 2 | 3 | 4 MACETerrain-Adaptive Locomotion Skills Using Deep Reinforcement Learning , Peng X., Berseth G., van de Panne M. (2016). ποΈ | ποΈ A3CAsynchronous Methods for Deep Reinforcement Learning , Mnih V. et al 2016. ποΈ 1 | 2 |Β 3 SACSoft Actor-Critic : Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor , Haarnoja T. et al. (2018). ποΈ MPOMaximum a Posteriori Policy Optimisation , Abdolmaleki A. et al (2018).A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms , Zhang S., Laroche R. et al. (2020).
DynaIntegrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming , Sutton R. (1990).PILCOPILCO: A Model-Based and Data-Efficient Approach to Policy Search , Deisenroth M., Rasmussen C. (2011). (talk )DBNProbabilistic MDP-behavior planning for cars , Brechtel S. et al. (2011).GPSEnd-to-End Training of Deep Visuomotor Policies , Levine S. et al. (2015). ποΈ DeepMPCDeepMPC: Learning Deep Latent Features for Model Predictive Control , Lenz I. et al. (2015). ποΈ SVGLearning Continuous Control Policies by Stochastic Value Gradients , Heess N. et al. (2015). ποΈ FARNNNonlinear Systems Identification Using Deep Dynamic Neural Networks , Ogunmolu O. et al. (2016). Optimal control with learned local models: Application to dexterous manipulation , Kumar V. et al. (2016). ποΈ BPTTLong-term Planning by Short-term Prediction , Shalev-Shwartz S. et al. (2016). ποΈ 1 | 2 Deep visual foresight for planning robot motion , Finn C., Levine S. (2016). ποΈ VINValue Iteration Networks , Tamar A. et al (2016). ποΈ VPNValue Prediction Network , Oh J. et al. (2017).DistGBPModel-Based Planning with Discrete and Continuous Actions , Henaff M. et al. (2017). ποΈ 1 | 2 Prediction and Control with Temporal Segment Models , Mishra N. et al. (2017).PredictronThe Predictron: End-To-End Learning and Planning , Silver D. et al. (2017). ποΈ MPPIInformation Theoretic MPC for Model-Based Reinforcement Learning , Williams G. et al. (2017). ποΈ Learning Real-World Robot Policies by Dreaming , Piergiovanni A. et al. (2018).Coupled Longitudinal and Lateral Control of a Vehicle using Deep Learning , Devineau G., Polack P., AlchtΓ© F., Moutarde F. (2018) ποΈ PlaNetLearning Latent Dynamics for Planning from Pixels , Hafner et al. (2018). ποΈ NeuralLanderNeural Lander: Stable Drone Landing Control using Learned Dynamics , Shi G. et al. (2018). ποΈ DBN+POMCPTowards Human-Like Prediction and Decision-Making for Automated Vehicles in Highway Scenarios , Sierra Gonzalez D. (2019).Planning with Goal-Conditioned Policies , Nasiriany S. et al. (2019). ποΈ MuZeroMastering Atari, Go, Chess and Shogi by Planning with a Learned Model , Schrittwiese J. et al. (2019). BADGRBADGR: An Autonomous Self-Supervised Learning-Based Navigation System , Kahn G., Abbeel P., Levine S. (2020). ποΈ H-UCRLEfficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning , Curi S., Berkenkamp F., Krause A. (2020).
Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear , Lipton Z. et al. (2016).Pseudo-countUnifying Count-Based Exploration and Intrinsic Motivation , Bellemare M. et al (2016). ποΈ HERHindsight Experience Replay , Andrychowicz M. et al. (2017). ποΈ VHERVisual Hindsight Experience Replay , Sahni H. et al. (2019).RNDExploration by Random Network Distillation , Burda Y. et al. (OpenAI) (2018). ποΈ Go-ExploreGo-Explore: a New Approach for Hard-Exploration Problems , Ecoffet A. et al. (Uber) (2018). ποΈ C51-IDSInformation-Directed Exploration for Deep Reinforcement Learning , Nikolov N., Kirschner J., Berkenkamp F., Krause A. (2019). Plan2ExplorePlanning to Explore via Self-Supervised World Models , Sekar R. et al. (2020). ποΈ RIDERIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments , Raileanu R., RocktΓ€schel T., (2020).
Hierarchy and Temporal Abstraction π
Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning , Sutton R. et al. (1999).Intrinsically motivated learning of hierarchical collections of skills , Barto A. et al. (2004).OCThe Option-Critic Architecture , Bacon P-L., Harb J., Precup D. (2016).Learning and Transfer of Modulated Locomotor Controllers , Heess N. et al. (2016). ποΈ Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving , Shalev-Shwartz S. et al. (2016).FuNsFeUdal Networks for Hierarchical Reinforcement Learning , Vezhnevets A. et al. (2017).Combining Neural Networks and Tree Search for Task and Motion Planning in Challenging Environments , Paxton C. et al. (2017). ποΈ DeepLocoDeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning , Peng X. et al. (2017). ποΈ | ποΈ Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play , Mahjourian R. et al (2018). ποΈ DACDAC: The Double Actor-Critic Architecture for Learning Options , Zhang S., Whiteson S. (2019).Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real , Nachum O. et al (2019). ποΈ SoftCon: Simulation and Control of Soft-Bodied Animals with Biomimetic Actuators , Min S. et al. (2020). ποΈ H-REILReinforcement Learning based Control of Imitative Policies for Near-Accident Driving , Cao Z. et al. (2020). ποΈ 1 , 2
Partial Observability ποΈ
PBVIPoint-based Value Iteration: An anytime algorithm for POMDPs , Pineau J. et al. (2003).cPBVIPoint-Based Value Iteration for Continuous POMDPs , Porta J. et al. (2006).POMCPMonte-Carlo Planning in Large POMDPs , Silver D., Veness J. (2010).A POMDP Approach to Robot Motion Planning under Uncertainty , Du Y. et al. (2010).Probabilistic Online POMDP Decision Making for Lane Changes in Fully Automated Driving , Ulbrich S., Maurer M. (2013).Solving Continuous POMDPs: Value Iteration with Incremental Learning of an Efficient Space Representation , Brechtel S. et al. (2013).Probabilistic Decision-Making under Uncertainty for Autonomous Driving using Continuous POMDPs , Brechtel S. et al. (2014).MOMDPIntention-Aware Motion Planning , Bandyopadhyay T. et al. (2013).DNCHybrid computing using a neural network with dynamic external memory , Graves A. et al (2016). ποΈ The value of inferring the internal state of traffic participants for autonomous freeway driving , Sunberg Z. et al. (2017).Belief State Planning for Autonomously Navigating Urban Intersections , Bouton M., Cosgun A., Kochenderfer M. (2017).Scalable Decision Making with Sensor Occlusions for Autonomous Driving , Bouton M. et al. (2018).Probabilistic Decision-Making at Road Intersections: Formulation and Quantitative Evaluation , Barbier M., Laugier C., Simonin O., Ibanez J. (2018).Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing , Kaufmann E. et al. (2018). ποΈ social perceptionBehavior Planning of Autonomous Cars with Social Perception , Sun L. et al (2019).
IT&ERobots that can adapt like animals , Cully A., Clune J., Tarapore D., Mouret J-B. (2014). ποΈ MAMLModel-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , Finn C., Abbeel P., Levine S. (2017). ποΈ Virtual to Real Reinforcement Learning for Autonomous Driving , Pan X. et al. (2017). ποΈ Sim-to-Real: Learning Agile Locomotion For Quadruped Robots , Tan J. et al. (2018). ποΈ ME-TRPOModel-Ensemble Trust-Region Policy Optimization , Kurutach T. et al. (2018). ποΈ Kickstarting Deep Reinforcement Learning , Schmitt S. et al. (2018).Learning Dexterous In-Hand Manipulation , OpenAI (2018). ποΈ GrBAL / ReBALLearning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning , Nagabandi A. et al. (2018). ποΈ Learning agile and dynamic motor skills for legged robots , Hwangbo J. et al. (ETH Zurich / Intel ISL) (2019). ποΈ Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning , Lee J., Hwangbo J., Hutter M. (ETH Zurich RSL) (2019)IT&ELearning and adapting quadruped gaits with the "Intelligent Trial & Error" algorithm , Dalin E., Desreumaux P., Mouret J-B. (2019). ποΈ FAMLEFast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priors , Kaushik R., Anne T., Mouret J-B. (2020). ποΈ Robust Deep Reinforcement Learning against Adversarial Perturbations on Observations , Zhang H. et al (2020). Learning quadrupedal locomotion over challenging terrain , Lee J. et al. (2020). ποΈ PACOHPACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees , Rothfuss J., Fortuin V., Josifoski M., Krause A. (2021).Model-Based Domain Generalization , Robey A. et al. (2021).SimGANSimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning , Jiang Y. et al. (2021). ποΈ Learning robust perceptive locomotion for quadrupedal robots in the wild , Miki T. et al. (2022).
Minimax-QMarkov games as a framework for multi-agent reinforcement learning , M. Littman (1994).Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems , Albrecht S., Stone P. (2017).MILPTime-optimal coordination of mobile robots along specified paths , AltchΓ© F. et al. (2016). ποΈ MIQPAn Algorithm for Supervised Driving of Cooperative Semi-Autonomous Vehicles , AltchΓ© F. et al. (2017). ποΈ SA-CADRLSocially Aware Motion Planning with Deep Reinforcement Learning , Chen Y. et al. (2017). ποΈ Multipolicy decision-making for autonomous driving via changepoint-based behavior prediction: Theory and experiment , Galceran E. et al. (2017).Online decision-making for scalable autonomous systems , Wray K. et al. (2017).MAgentMAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence , Zheng L. et al. (2017). ποΈ Cooperative Motion Planning for Non-Holonomic Agents with Value Iteration Networks , Rehder E. et al. (2017).MPPOTowards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning , Long P. et al. (2017). ποΈ COMACounterfactual Multi-Agent Policy Gradients , Foerster J. et al. (2017).MADDPGMulti-Agent Actor-Critic for Mixed Cooperative-Competitive Environments , Lowe R. et al (2017). FTWHuman-level performance in first-person multiplayer games with population-based deep reinforcement learning , Jaderberg M. et al. (2018). ποΈ Towards Learning Multi-agent Negotiations via Self-Play , Tang Y. C. (2020).MAPPOThe Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games , Yu C. et al. (2021). |:octocat:](https://github.com/marlbenchmark/on-policy )Many-agent Reinforcement Learning , Yang Y. (2021)
Variable Resolution Discretization in Optimal Control , Munos R., Moore A. (2002). ποΈ DeepDrivingDeepDriving: Learning Affordance for Direct Perception in Autonomous Driving , Chen C. et al. (2015). ποΈ On the Sample Complexity of End-to-end Training vs. Semantic Abstraction Training , Shalev-Shwartz S. et al. (2016).Learning sparse representations in reinforcement learning with sparse coding , Le L., Kumaraswamy M., White M. (2017).World Models , Ha D., Schmidhuber J. (2018). ποΈ Learning to Drive in a Day , Kendall A. et al. (2018). ποΈ MERLINUnsupervised Predictive Memory in a Goal-Directed Agent , Wayne G. et al. (2018). ποΈ 1 | 2 | 3 | 4 | 5 | 6 Variational End-to-End Navigation and Localization , Amini A. et al. (2018). ποΈ Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks , Lee M. et al. (2018). ποΈ Deep Neuroevolution of Recurrent and Discrete World Models , Risi S., Stanley K.O. (2019). ποΈ FERMA Framework for Efficient Robotic Manipulation , Zhan A., Zhao R. et al. (2021). S4RLS4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning , Sinha S. et al (2021).
Is the Bellman residual a bad proxy? , Geist M., Piot B., Pietquin O. (2016).Deep Reinforcement Learning that Matters , Henderson P. et al. (2017).Automatic Bridge Bidding Using Deep Reinforcement Learning , Yeh C. and Lin H. (2016).Shared Autonomy via Deep Reinforcement Learning , Reddy S. et al. (2018). ποΈ Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review , Levine S. (2018).The Value Function Polytope in Reinforcement Learning , Dadashi R. et al. (2019).On Value Functions and the Agent-Environment Boundary , Jiang N. (2019).How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned , Ibartz J. et al (2021).
Learning from Demonstrations π
DAggerA Reduction of Imitation Learning and Structured Predictionto No-Regret Online Learning , Ross S., Gordon G., Bagnell J. A. (2011).QMDP-RCNNReinforcement Learning via Recurrent Convolutional Neural Networks , Shankar T. et al. (2016). (talk )DQfDLearning from Demonstrations for Real World Reinforcement Learning , Hester T. et al. (2017). ποΈ Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy , Barnes D., Maddern W., Posner I. (2016). ποΈ GAILGenerative Adversarial Imitation Learning , Ho J., Ermon S. (2016).From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots , Pfeiffer M. et al. (2017). ποΈ BranchedEnd-to-end Driving via Conditional Imitation Learning , Codevilla F. et al. (2017). ποΈ | talk UPNUniversal Planning Networks , Srinivas A. et al. (2018). ποΈ DeepMimicDeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills , Peng X. B. et al. (2018). ποΈ R2P2Deep Imitative Models for Flexible Inference, Planning, and Control , Rhinehart N. et al. (2018). ποΈ Learning Agile Robotic Locomotion Skills by Imitating Animals , Bin Peng X. et al (2020). ποΈ Deep Imitative Models for Flexible Inference, Planning, and Control , Rhinehart N., McAllister R., Levine S. (2020).
Applications to Autonomous Driving π
ALVINN, an autonomous land vehicle in a neural network , Pomerleau D. (1989).End to End Learning for Self-Driving Cars , Bojarski M. et al. (2016). ποΈ End-to-end Learning of Driving Models from Large-scale Video Datasets , Xu H., Gao Y. et al. (2016). ποΈ End-to-End Deep Learning for Steering Autonomous Vehicles Considering Temporal Dependencies , Eraqi H. et al. (2017).Driving Like a Human: Imitation Learning for Path Planning using Convolutional Neural Networks , Rehder E. et al. (2017).Imitating Driver Behavior with Generative Adversarial Networks , Kuefler A. et al. (2017).PS-GAILMulti-Agent Imitation Learning for Driving Simulation , Bhattacharyya R. et al. (2018). ποΈ Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety , Chen J. et al. (2019).
Inverse Reinforcement Learning
ProjectionApprenticeship learning via inverse reinforcement learning , Abbeel P., Ng A. (2004).MMPMaximum margin planning , Ratliff N. et al. (2006).BIRLBayesian inverse reinforcement learning , Ramachandran D., Amir E. (2007).MEIRLMaximum Entropy Inverse Reinforcement Learning , Ziebart B. et al. (2008).LEARCHLearning to search: Functional gradient techniques for imitation learning , Ratliff N., Siver D. Bagnell A. (2009).CIOCContinuous Inverse Optimal Control with Locally Optimal Examples , Levine S., Koltun V. (2012). ποΈ MEDIRLMaximum Entropy Deep Inverse Reinforcement Learning , Wulfmeier M. (2015).GCLGuided Cost Learning: Deep Inverse Optimal Control via Policy Optimization , Finn C. et al. (2016). ποΈ RIRLRepeated Inverse Reinforcement Learning , Amin K. et al. (2017).Bridging the Gap Between Imitation Learning and Inverse Reinforcement Learning , Piot B. et al. (2017).
Applications to Autonomous Driving π
Apprenticeship Learning for Motion Planning, with Application to Parking Lot Navigation , Abbeel P. et al. (2008).Navigate like a cabbie: Probabilistic reasoning from observed context-aware behavior , Ziebart B. et al. (2008).Planning-based Prediction for Pedestrians , Ziebart B. et al. (2009). ποΈ Learning for autonomous navigation , Bagnell A. et al. (2010).Learning Autonomous Driving Styles and Maneuvers from Expert Demonstration , Silver D. et al. (2012).Learning Driving Styles for Autonomous Vehicles from Demonstration , Kuderer M. et al. (2015).Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks , Sharifzadeh S. et al. (2016).Watch This: Scalable Cost-Function Learning for Path Planning in Urban Environments , Wulfmeier M. (2016). ποΈ Planning for Autonomous Cars that Leverage Effects on Human Actions , Sadigh D. et al. (2016).A Learning-Based Framework for Handling Dilemmas in Urban Automated Driving , Lee S., Seo S. (2017).Learning Trajectory Prediction with Continuous Inverse Optimal Control via Langevin Sampling of Energy-Based Models , Xu Y. et al. (2019).Analyzing the Suitability of Cost Functions for Explaining and Imitating Human Driving Behavior based on Inverse Reinforcement Learning , Naumann M. et al (2020).
Motion Planning πββοΈ
DijkstraA Note on Two Problems in Connexion with Graphs , Dijkstra E. W. (1959).A* A Formal Basis for the Heuristic Determination of Minimum Cost Paths , Hart P. et al. (1968).Planning Long Dynamically-Feasible Maneuvers For Autonomous Vehicles , Likhachev M., Ferguson D. (2008).Optimal Trajectory Generation for Dynamic Street Scenarios in a Frenet Frame , Werling M., Kammel S. (2010). ποΈ 3D perception and planning for self-driving and cooperative automobiles , Stiller C., Ziegler J. (2012).Motion Planning under Uncertainty for On-Road Autonomous Driving , Xu W. et al. (2014).Monte Carlo Tree Search for Simulated Car Racing , Fischer J. et al. (2015). ποΈ
Architecture and applications
You canβt perform that action at this time.
ποΈ